Back to directory

Inkeep Agents

An open-source platform for building AI agents either in a no-code visual builder or a TypeScript SDK, with the two kept in two-way sync so technical and non-technical teams can edit the same agents.

Inkeep Agents

Inkeep Agents lets a team build AI agents through a drag-and-drop visual builder, a code-first TypeScript SDK, or both at once, since edits in either format stay synced. Agents built this way can act as real-time chat assistants, such as a customer-support agent for help centers or an internal copilot for other teams, or run AI workflow automation such as updating knowledge bases and documentation, or triaging helpdesk tickets.

The open-source platform includes an API that configures agents, sub-agents, MCP servers, credentials and projects and tracks conversation state with OpenTelemetry traces, a management UI that talks to that API, a TypeScript SDK for defining agents and tools in code, and a CLI for pushing and pulling agent definitions. Agents can be triggered through MCP, the A2A protocol or the Vercel AI SDK, and it deploys with Vercel or Docker.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.